Complexity to Resilience: Machine Learning Models for Enhancing Supply Chains and Resilience in the Middle Eastern Trade Corridor Nations

The durable nature of supply chains in the Middle Eastern region is critical, given the region’s strategic role in global trade corridors, yet geopolitical conflicts, territorial disputes, and governance challenges persistently disrupt key routes like the Suez Canal, amplifying vulnerabilities. This study addresses the urgent need to predict and mitigate supply chain risks by evaluating machine learning (ML) models for forecasting economic complexity as a proxy for resilience across 18 Middle Eastern countries. Using a multidimensional secondary dataset, we compare gated recurrent unit (GRU), support vector regression (SVR), gradient boosting, and other ensemble models, assessing performance via MSE, MAE, RMSE, and R2. The results demonstrate the GRU model’s superior accuracy (R2 = 0.9813; MSE = 0.0011), with SHAP, sensitivity, and sensitivity analysis confirming its robustness in identifying resilience determinants. Analyses reveal infrastructure quality and natural resource rents as pivotal factors influencing the economic complexity index (ECI), while disruptions like trade embargoes or infrastructure failures significantly degrade resilience. Our findings underscore the importance of diversifying infrastructure investments and stabilizing governance frameworks to buffer against shocks. This research advances the application of deep learning in supply chain resilience analytics, offering actionable insights for policymakers and logistics planners to fortify regional trade corridors and mitigate global ripple effects.